Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10005
    Prev
    Next
    INDEX
    Explanations

    sections of high uncertainty or speculation, often indicated by hedging or qualifying language.

    oai_token-act-pair · gpt-4oTriggered by @dh

    punctuation characters and their usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -1.06
    (
    -0.92
     (
    -0.75
     (
    
    -0.75
    (
    -0.74
     (__
    -0.73
     ($\
    -0.69
     snippetHide
    -0.65
     $($
    -0.64
     $(\
    -0.64
    POSITIVE LOGITS
    "]))
    0.90
     referenties
    0.87
    }))
    0.87
    ']))
    0.85
    ")))
    0.83
    ]))
    0.81
    "]));
    0.81
    ])).
    0.80
    ++]
    0.79
    ])),
    0.78
    Activations Density 0.468%

    No Known Activations